Newer
Older
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
" <th>Locke</th>\n",
" <td>Terry O'Quinn</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sawyer</th>\n",
" <td>Josh Holloway</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Walt</th>\n",
" <td>Malcolm David Kelley</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Actor Main Cast\n",
"Character \n",
"Hurley Jorge Garcia True\n",
"Jack Matthew Fox True\n",
"Kate Evangeline Lilly True\n",
"Locke Terry O'Quinn True\n",
"Sawyer Josh Holloway True\n",
"Walt Malcolm David Kelley False"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.read_json(\"lost.json\").set_index(\"Character\").sort_index()"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## Task 2\n",
"<a name=\"task2\"></a>\n",
"\n",
"* Read in `nest-data.csv` to `DataFrame`; call it `df`\n",
"* Get to know it and play a bit with it\n",
"* Tell me when you're done: [pollev.com/aherten538](https://pollev.com/aherten538)"
"execution_count": 30,
"metadata": {
"exercise": "task"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"id,Nodes,Tasks/Node,Threads/Task,Runtime Program / s,Scale,Plastic,Avg. Neuron Build Time / s,Min. Edge Build Time / s,Max. Edge Build Time / s,Min. Init. Time / s,Max. Init. Time / s,Presim. Time / s,Sim. Time / s,Virt. Memory (Sum) / kB,Local Spike Counter (Sum),Average Rate (Sum),Number of Neurons,Number of Connections,Min. Delay,Max. Delay\n",
"5,1,2,4,420.42,10,true,0.29,88.12,88.18,1.14,1.20,17.26,311.52,46560664.00,825499,7.48,112500,1265738500,1.5,1.5\n",
"5,1,4,4,200.84,10,true,0.15,46.03,46.34,0.70,1.01,7.87,142.97,46903088.00,802865,7.03,112500,1265738500,1.5,1.5\n"
]
}
],
"source": [
"!cat nest-data.csv | head -3"
]
},
{
"cell_type": "code",
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
"slideshow": {
"slide_type": "fragment"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>Nodes</th>\n",
" <th>Tasks/Node</th>\n",
" <th>Threads/Task</th>\n",
" <th>Runtime Program / s</th>\n",
" <th>Scale</th>\n",
" <th>Plastic</th>\n",
" <th>Avg. Neuron Build Time / s</th>\n",
" <th>Min. Edge Build Time / s</th>\n",
" <th>Max. Edge Build Time / s</th>\n",
" <th>...</th>\n",
" <th>Max. Init. Time / s</th>\n",
" <th>Presim. Time / s</th>\n",
" <th>Sim. Time / s</th>\n",
" <th>Virt. Memory (Sum) / kB</th>\n",
" <th>Local Spike Counter (Sum)</th>\n",
" <th>Average Rate (Sum)</th>\n",
" <th>Number of Neurons</th>\n",
" <th>Number of Connections</th>\n",
" <th>Min. Delay</th>\n",
" <th>Max. Delay</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>420.42</td>\n",
" <td>10</td>\n",
" <td>True</td>\n",
" <td>0.29</td>\n",
" <td>88.12</td>\n",
" <td>88.18</td>\n",
" <td>...</td>\n",
" <td>1.20</td>\n",
" <td>17.26</td>\n",
" <td>311.52</td>\n",
" <td>46560664.0</td>\n",
" <td>825499</td>\n",
" <td>7.48</td>\n",
" <td>112500</td>\n",
" <td>1265738500</td>\n",
" <td>1.5</td>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>200.84</td>\n",
" <td>10</td>\n",
" <td>True</td>\n",
" <td>0.15</td>\n",
" <td>46.03</td>\n",
" <td>46.34</td>\n",
" <td>...</td>\n",
" <td>1.01</td>\n",
" <td>7.87</td>\n",
" <td>142.97</td>\n",
" <td>46903088.0</td>\n",
" <td>802865</td>\n",
" <td>7.03</td>\n",
" <td>112500</td>\n",
" <td>1265738500</td>\n",
" <td>1.5</td>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>202.15</td>\n",
" <td>10</td>\n",
" <td>True</td>\n",
" <td>0.28</td>\n",
" <td>47.98</td>\n",
" <td>48.48</td>\n",
" <td>...</td>\n",
" <td>1.20</td>\n",
" <td>7.95</td>\n",
" <td>142.81</td>\n",
" <td>47699384.0</td>\n",
" <td>802865</td>\n",
" <td>7.03</td>\n",
" <td>112500</td>\n",
" <td>1265738500</td>\n",
" <td>1.5</td>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>89.57</td>\n",
" <td>10</td>\n",
" <td>True</td>\n",
" <td>0.15</td>\n",
" <td>20.41</td>\n",
" <td>23.21</td>\n",
" <td>...</td>\n",
" <td>3.04</td>\n",
" <td>3.19</td>\n",
" <td>60.31</td>\n",
" <td>46813040.0</td>\n",
" <td>821491</td>\n",
" <td>7.23</td>\n",
" <td>112500</td>\n",
" <td>1265738500</td>\n",
" <td>1.5</td>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>164.16</td>\n",
" <td>10</td>\n",
" <td>True</td>\n",
" <td>0.20</td>\n",
" <td>40.03</td>\n",
" <td>41.09</td>\n",
" <td>...</td>\n",
" <td>1.58</td>\n",
" <td>6.08</td>\n",
" <td>114.88</td>\n",
" <td>46937216.0</td>\n",
" <td>802865</td>\n",
" <td>7.03</td>\n",
" <td>112500</td>\n",
" <td>1265738500</td>\n",
" <td>1.5</td>\n",
" <td>1.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 21 columns</p>\n",
"</div>"
],
"text/plain": [
" id Nodes Tasks/Node Threads/Task Runtime Program / s Scale Plastic \\\n",
"0 5 1 2 4 420.42 10 True \n",
"1 5 1 4 4 200.84 10 True \n",
"2 5 1 2 8 202.15 10 True \n",
"3 5 1 4 8 89.57 10 True \n",
"4 5 2 2 4 164.16 10 True \n",
"\n",
" Avg. Neuron Build Time / s Min. Edge Build Time / s \\\n",
"0 0.29 88.12 \n",
"1 0.15 46.03 \n",
"2 0.28 47.98 \n",
"3 0.15 20.41 \n",
"4 0.20 40.03 \n",
"\n",
" Max. Edge Build Time / s ... Max. Init. Time / s Presim. Time / s \\\n",
"0 88.18 ... 1.20 17.26 \n",
"1 46.34 ... 1.01 7.87 \n",
"2 48.48 ... 1.20 7.95 \n",
"3 23.21 ... 3.04 3.19 \n",
"4 41.09 ... 1.58 6.08 \n",
"\n",
" Sim. Time / s Virt. Memory (Sum) / kB Local Spike Counter (Sum) \\\n",
"0 311.52 46560664.0 825499 \n",
"1 142.97 46903088.0 802865 \n",
"2 142.81 47699384.0 802865 \n",
"3 60.31 46813040.0 821491 \n",
"4 114.88 46937216.0 802865 \n",
"\n",
" Average Rate (Sum) Number of Neurons Number of Connections Min. Delay \\\n",
"0 7.48 112500 1265738500 1.5 \n",
"1 7.03 112500 1265738500 1.5 \n",
"2 7.03 112500 1265738500 1.5 \n",
"3 7.23 112500 1265738500 1.5 \n",
"4 7.03 112500 1265738500 1.5 \n",
"\n",
" Max. Delay \n",
"0 1.5 \n",
"1 1.5 \n",
"2 1.5 \n",
"3 1.5 \n",
"4 1.5 \n",
"\n",
"[5 rows x 21 columns]"
]
},
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"nest-data.csv\")\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## Read CSV Options\n",
"\n",
"* See also full [API documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.read_csv.html)\n",
"* Important parameters\n",
" - `sep`: Set separator (for example `:` instead of `,`)\n",
" - `header`: Specify info about headers for columns; able to use multi-index for columns!\n",
" - `names`: Alternative to `header` – provide your own column titles\n",
" - `usecols`: Don't read whole set of columns, but only these; works with any list (`range(0:20:2)`)…\n",
" - `skiprows`: Don't read in these rows\n",
" - `na_values`: What string(s) to recognize as `N/A` values (which will be ignored during operations on data frame)\n",
" - `parse_dates`: Try to parse dates in CSV; different behaviours as to provided data structure; optionally used together with `date_parser`\n",
" - `compression`: Treat input file as compressed file (\"infer\", \"gzip\", \"zip\", …)\n",
" - `decimal`: Decimal point divider – for German data…\n",
" \n",
"```python\n",
"pandas.read_csv(filepath_or_buffer, sep=', ', delimiter=None, header='infer', names=None, index_col=None, usecols=None, squeeze=False, prefix=None, mangle_dupe_cols=True, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, dayfirst=False, iterator=False, chunksize=None, compression='infer', thousands=None, decimal=b'.', lineterminator=None, quotechar='\"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, dialect=None, tupleize_cols=None, error_bad_lines=True, warn_bad_lines=True, delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None)\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## Slicing of Data Frames\n",
"\n",
"### Slicing Columns\n",
"\n",
"* Use square-bracket operators to slice data frame: `[]`\n",
" * Use column name to select column\n",
" * Also: Slice horizontally\n",
"* Example: Select only columnn `C` from `df_demo`"
]
},
{
"cell_type": "code",
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.2</td>\n",
" <td>-2.718282</td>\n",
" <td>This</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.2</td>\n",
" <td>1.718282</td>\n",
" <td>column</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.2</td>\n",
" <td>-1.304068</td>\n",
" <td>has</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"0 1.2 2018-02-26 -2.718282 This Same\n",
"1 1.2 2018-02-26 1.718282 column Same\n",
"2 1.2 2018-02-26 -1.304068 has Same"
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo.head(3)"
]
},
{
"cell_type": "code",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 -2.718282\n",
"1 1.718282\n",
"2 -1.304068\n",
"3 0.986231\n",
"4 -0.718282\n",
"Name: C, dtype: float64"
]
},
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo[\"C\"]"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"* Select more than one column by providing list `[]` to slice operator `[]`\n",
"* *You usually end up forgett one of the brackets…*\n",
"* Example: Select list of columns `A` and `C`, `[\"A\", \"C\"]` from `df_demo`"
]
},
{
"cell_type": "code",
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
"metadata": {
"slideshow": {
"slide_type": "fragment"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>C</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.2</td>\n",
" <td>-2.718282</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.2</td>\n",
" <td>1.718282</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.2</td>\n",
" <td>-1.304068</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.2</td>\n",
" <td>0.986231</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.2</td>\n",
" <td>-0.718282</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A C\n",
"0 1.2 -2.718282\n",
"1 1.2 1.718282\n",
"2 1.2 -1.304068\n",
"3 1.2 0.986231\n",
"4 1.2 -0.718282"
]
},
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo[[\"A\", \"C\"]]"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"## Slicing of Data Frames\n",
"\n",
"### Slicing rows\n",
"\n",
"* Use numberical values to slice into rows\n",
"* Use ranges just like with Python lists"
]
},
{
"cell_type": "code",
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.2</td>\n",
" <td>1.718282</td>\n",
" <td>column</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.2</td>\n",
" <td>-1.304068</td>\n",
" <td>has</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"1 1.2 2018-02-26 1.718282 column Same\n",
"2 1.2 2018-02-26 -1.304068 has Same"
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo[1:3]"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "fragment"
}
},
"source": [
"* Get a certain range as **per the current sort structure**"
]
},
{
"cell_type": "code",
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.2</td>\n",
" <td>2018-02-26</td>\n",
" <td>1.718282</td>\n",
" <td>column</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.2</td>\n",
" <td>2018-02-26</td>\n",
" <td>-1.304068</td>\n",
" <td>has</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"1 1.2 2018-02-26 1.718282 column Same\n",
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo.iloc[1:3]"
]
},
{
"cell_type": "code",
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.2</td>\n",
" <td>2018-02-26</td>\n",
" <td>1.718282</td>\n",
" <td>column</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.2</td>\n",
" <td>2018-02-26</td>\n",
" <td>0.986231</td>\n",
" <td>entries</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"1 1.2 2018-02-26 1.718282 column Same\n",
"3 1.2 2018-02-26 0.986231 entries Same"
]
},
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo.iloc[1:6:2]"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"* Attention: `.iloc[]` location might change after re-sorting!"
]
},
{
"cell_type": "code",
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
"metadata": {
"slideshow": {
"slide_type": "fragment"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.2</td>\n",
" <td>-1.304068</td>\n",
" <td>has</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.2</td>\n",
" <td>-0.718282</td>\n",
" <td>entries</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2 1.2 2018-02-26 -1.304068 has Same\n",
"4 1.2 2018-02-26 -0.718282 entries Same"
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo.sort_values(\"C\").iloc[1:3]"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"* One more row-slicing option: `.loc[]`\n",
"* See the difference with a *proper* index (and not the auto-generated default index from before)"
]
},
{
"cell_type": "code",
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
"metadata": {
"slideshow": {
"slide_type": "fragment"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>E</th>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>This</th>\n",
" <td>1.2</td>\n",
" <td>-2.718282</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>column</th>\n",
" <td>1.2</td>\n",
" <td>1.718282</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>has</th>\n",
" <td>1.2</td>\n",
" <td>-1.304068</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>entries</th>\n",
" <td>1.2</td>\n",
" <td>0.986231</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" <tr>\n",
" <th>entries</th>\n",
" <td>1.2</td>\n",
" <td>-0.718282</td>\n",
" <td>Same</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C E\n",
"D \n",
"This 1.2 2018-02-26 -2.718282 Same\n",
"column 1.2 2018-02-26 1.718282 Same\n",
"has 1.2 2018-02-26 -1.304068 Same\n",
"entries 1.2 2018-02-26 0.986231 Same\n",
"entries 1.2 2018-02-26 -0.718282 Same"
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_demo_indexed = df_demo.set_index(\"D\")\n",
"df_demo_indexed"
]
},
{
"cell_type": "code",